Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

VideoMAE BDSLW60 U5 20 CoR New

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set: Loss: 0.1917 Accuracy: 0.9717

Quellehuggingface.co/Shawon16/videoMAE_BDSLW60_U5_20_coR_new/tree/1559d733d05fd20a8834318c4e2dd559ba616d28
ArtOtherBasismodellMCG-NJU/videomae-base-finetuned-kineticsVersionRevision 1559d73BBewertung

Modellquelle

Art
Other
Dateigröße
329 MB
Basismodell
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision 1559d73
Aktualisiert
24. Okt. 2026
Downloads
19
Quelle
Hugging Face

Quellenbeschreibung

videoMAE_BDSLW60_U5_20_coR_new

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1917
  • Accuracy: 0.9717

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 18560
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
10.53560.05019290.83950.915
0.79411.050118580.16470.9517
0.15182.050127870.17610.97
0.09763.050137160.18430.9517
0.10914.050146450.19570.9567
0.10125.050155740.09350.98
0.09086.050165030.20950.96
0.10967.050174320.31950.945
0.06648.050183610.20690.9617
0.06719.050192900.44010.9483
0.044610.0501102190.09130.9833
0.032911.0501111480.20720.9617
0.051112.0501120770.27060.9567
0.037913.0501130060.14030.9683
0.029314.0501139350.15470.9633
0.017115.0501148640.19170.9717

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.1.0
  • Tokenizers 0.20.1

Quellen

1 Quelle
Hugging FacePrimärVersion 1559d733d05fd20a8834318c4e2dd559ba616d28
huggingface.co/Shawon16/videoMAE_BDSLW60_U5_20_coR_new/tree/1559d733d05fd20a8834318c4e2dd559ba616d28

Verifiziert 24. Okt.

Modellartefakte

1 Artefakt

model.safetensors

safetensors · 329 MB · SHA-256 8c1ffbd57e1e…a211 · Hugging Face

Download file

Quellenauszüge

3 Auszüge
Readme6. Aug.huggingface.co/Shawon16/videoMAE_BDSLW60_U5_20_coR_new

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy model-index: - name: videoMAE_BDSLW60_U5_20_coR_new results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # videoMAE_BDSLW60_U5_20_coR_new This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1917 - Accuracy: 0.9717 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 18560 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-------:|:-----:|:---------------:|:--------:| | 10.5356 | 0.0501 | 929 | 0.8395 | 0.915 | | 0.7941 | 1.0501 | 1858 | 0.1647 | 0.9517 | | 0.1518 | 2.0501 | 2787 | 0.1761 | 0.97 | | 0.0976 | 3.0501 | 3716 | 0.1843 | 0.9517 | | 0.1091 | 4.0501 | 4645 | 0.1957 | 0.9567 | | 0.1012 | 5.0501 | 5574 | 0.0935 | 0.98 | | 0.0908 | 6.0501 | 6503 | 0.2095 | 0.96 | | 0.1096 | 7.0501 | 7432 | 0.3195 | 0.945 | | 0.0664 | 8.0501 | 8361 | 0.2069 | 0.9617 | | 0.0671 | 9.0501 | 9290 | 0.4401 | 0.9483 | | 0.0446 | 10.0501 | 10219 | 0.0913 | 0.9833 | | 0.0329 | 11.0501 | 11148 | 0.2072 | 0.9617 | | 0.0511 | 12.0501 | 12077 | 0.2706 | 0.9567 | | 0.0379 | 13.0501 | 13006 | 0.1403 | 0.9683 | | 0.0293 | 14.0501 | 13935 | 0.1547 | 0.9633 | | 0.0171 | 15.0501 | 14864 | 0.1917 | 0.9717 | ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.1

Note24. Okt.huggingface.co/Shawon16/videoMAE_BDSLW60_U5_20_coR_new

Source context: 19 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/videoMAE_BDSLW60_U5_20_coR_new

Note6. Aug.huggingface.co/Shawon16/videoMAE_BDSLW60_U5_20_coR_new

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/videoMAE_BDSLW60_U5_20_coR_new